AI Runtime Engineer - Performance Optimization

Join the forefront of AI technology as a Runtime Engineer, focusing on optimizing execution layers for next-generation AI workloads. Your expertise will enhance performance, scalability, and reliability in a multi-hardware environment.In this pivotal role, you will develop a high-performance execution engine supporting diverse hardware architectures. Collaborate with compiler, hardware, and product teams to drive innovations in AI infrastructure. Your responsibilities will involve advanced workload scheduling, profiling binary execution, and creating diagnostic frameworks to enhance runtime efficiency.Key Responsibilities:
• Design and build a high-performance execution engine
• Optimize workload execution with scheduling and partitioning strategies
• Profile compiled workloads and identify performance improvements
• Develop tooling and telemetry for execution analysis
• Analyze runtime performance across various hardware configurationsRequirements:
• Experience in de...